Skip to main content

Daniel Zoran: From Learning Models of Natural Image Patches to Whole Image Restoration

Movies Preview

movies
Daniel Zoran: From Learning Models of Natural Image Patches to Whole Image Restoration


Published March 1, 2012


Talk by Daniel Zoran, from The Hebrew University of Jerusalem. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract.
Learning good image priors is of utmost importance for the study of vision, computer vision and image processing applications. Learning priors and optimizing over whole images can lead to tremendous computational challenges. In contrast, when we work with small image patches, it is possible to learn priors and perform patch restoration very efficiently. This raises three questions - do priors that give high likelihood to the data also lead to good performance in restoration? Can we use such patch based priors to restore a full image? Can we learn better patch priors? In this work we answer these questions. We compare the likelihood of several patch models and show that priors that give high likelihood to data perform better in patch restoration. Motivated by this result, we propose a generic framework which allows for whole image restoration using any patch based prior for which a MAP (or approximate MAP) estimate can be calculated. We show how to derive an appropriate cost function, how to optimize it and how to use it to restore whole images. Finally, we present a generic, surprisingly simple Gaussian Mixture prior, learned from a set of natural images. When used with the proposed framework, this Gaussian Mixture Model outperforms all other generic prior methods for image denoising, deblurring and inpainting. We will briefly discuss what can we learn about natural images by using such a prior, and its relation to other models. Joint work with Yair Weiss


Audio/Visual sound, color

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Community Video
movies
eye 14
favorite 0
comment 0
Community Video
movies
eye 301
favorite 1
comment 0
Community Video
movies
eye 530
favorite 0
comment 0
Community Video
by Redwood Center for Theoretical Neuroscience
movies
eye 282
favorite 0
comment 0
Community Video
by Morale Patch Armory
movies
eye 5
favorite 0
comment 0
Arxiv.org
by Sainbayar Sukhbaatar; Takaki Makino; Kazuyuki Aihara
texts
eye 23
favorite 0
comment 0
Source: http://arxiv.org/abs/1301.3323v4